You are on page 1of 15

NUMBER

PLATE
RECOGNITIO
Under the guidance of
N
Prof. M.P.Dave
USING
LABVIEW

Prepared by :
Rishi Mishra
(1002721084)
Rajat Sharma
(1002721080)
Pushkar Dubey
(1002721077)

EN-F 4th year

CONTENTS
introduction
Block diagram
Image acquisition
Vision Assistant

Original Image

Image mask
Color plane extraction
Threshold
Look up table
Optical Character Recognition (OCR)

Example

introduction

Real time application which recognizes license plates from cars at


gate.
The system is based on regular PC with video camera.
Catches video frames which includes a visible car license plate and
processes them.
Once a license plate is detected, its digit are recognized, displayed
he User Interface or checked against a database.
This project will focus on the design algorithms used for extracting
he license plate from a single image, isolating the characters of th
plate and identifying the individual characters.

Block diagram

Vision acquisition

The first step toward any kind of image processing is the acquisition of th
ctual images to be processed.

The images can be obtained from a camera (of which USB and DV are bu
wo possible varieties) or from a file stored on a local hard disk.

Once the images are obtained, they can be further processed by program
o extract whatever information is both desired and discernible from them

Vision assistant

After the initial stage of image acquisition, typical LPR systems

undergo image processing.


This includes
Original image
Image mask
Color plane extraction
Brightness
Find straight edges
Caliper
Set coordinate system
Threshold
Advance morphology
Look up table
Optical Character Recognition

Continued
OrigiA typical license plate is shown in figure.

Continued
Image mask: The block Image Mask 1, is used to

discard the borders of the image that are statistically


unlikely to contain the license plate, it is assumed the
license plate is not on the border of the image. This is
done to speed up the overall processing of the image.

Color plane extraction: Color Plane Extraction 1 is used


to convert the image into a gray-scale one as shown in
figure below.

Masked grayscale
image

Image mask

Color plane
extraction

Continued
Threshold:
Brightness, alters the brightness, contrast and gamma
of an image.

Background
Correction
Local Threshold

Continued

ook up table: Distributes the grayscale values evenly within a giv

ayscale range. Use to increase the contrast in images containing f


ayscale values.

Optical Character Recognition: A group of VIs that perform optica

aracter recognition in a region of the image. Following steps are


erformed in OCR:
The tool was previously trained on a set of characters and is
designed for
the size and spacing of the characters in the plate as shown
in figure
below.

Continued

The OCR Training Session

Continued

he OCR tool extracts unique features from each segmented object in the
mage and compares them to each character stored in the character set.
then returns the closest character from the character set that best matc
he object.
his can be shown by following diagram:

Next step

Our next step is to resize the image automatically.


After this step, there would be no need to adjust the
frame of image every time after taking an image.

U
O
Y

The threshold 1 block is used to


convert the gray-scale
image into a binary image in order to
easily distinguish between the
foreground (plate characters) and
the background (plate background).
A background correction local
threshold is used, since it minimizes
the non-uniform lighting effects, and
minimizes the noise in the
resulting binary image.

K
N
A
H
T

You might also like